© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14683
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function definition and error handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.01
    ↵↵
    -0.90
     (
    -0.89
      
    -0.87
    ↵
    -0.85
    <eos>
    -0.83
    ,
    -0.79
    -
    -0.77
    1
    -0.77
        
    -0.76
    POSITIVE LOGITS
     desmotivaciones
    1.45
     queſta
    1.43
    parsedMessage
    1.41
     indígen
    1.41
     ainfi
    1.35
    majánló
    1.33
     étoient
    1.30
     avoient
    1.30
    ⟬
    1.29
    RenderAtEndOf
    1.28
    Activations Density 0.230%

    No Known Activations